Get started
Author

Aolin Ding

Observed name: Ding, Aolin
ORCID: 0009-0007-0746-3031
Observed ORCID: 0009-0007-0746-3031
OpenAlex ID: A5040519309
H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking
2025 · Kuo, Martin, Zhang, Jianyi, et al. · arXiv (Cornell University) · 122
PDF
Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
2025 · Kuo, Martin, Zhang, Jingyang, et al. · arXiv (Cornell University) · 9
PDF
SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues
2025 · Kuo, Martin, Zhang, Jianyi, et al. · arXiv (Cornell University) · 8
PDF
FADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devices
2022 · Tang, Minxue, Zhang, Jianyi, et al. · arXiv (Cornell University) · 8
PDF
Build a Computationally Efficient Strong Defense Against Adversarial Example Attacks
2024 · Changwei Liu, Louis DiValentin, et al. · International Conference on Information Systems Security and Privacy (ICISSP) · 3
Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition
2026 · Tang, Minxue, Yu, Yangyang, et al. · arXiv (Cornell University) · 1
PDF
FedProphet: Memory-Efficient Federated Adversarial Training via Robust and Consistent Cascade Learning
2024 · Tang, Minxue, Wang, Yitu, et al. · arXiv (Cornell University) · 1
PDF
Evaluating Input Transformation Ensembles Against Adversarial Attacks
2025 · Changwei Liu, Louis DiValentin, et al. · Communications in computer and information science
Works count: 8
Citation count: 152
H-index: 4
I10-index: 1
Year
Topic
Type